4.7 Article

Federated Learning With NOMA Assisted by Multiple Intelligent Reflecting Surfaces: Latency Minimizing Optimization and Auction

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Information Systems

Latency Minimization for IRS-Aided NOMA MEC Systems With WPT-Enabled IoT Devices

Gen Li et al.

Summary: Mobile-edge computing (MEC) and intelligent reflecting surface (IRS) are two promising technologies for massive connectivity in future IoT networks. MEC allows IoT devices (IDs) to offload computation tasks and extend their lifespan, while IRS enhances the channel condition between IDs and access points (APs) within the MEC system. The article applies IRS in a multi-ID MEC system to improve latency performance through a hybrid multiple access scheme and a timing protocol for the IDs. It also tackles the latency optimization problem with joint optimization of power allocation, IRS phase shift matrix, and uplink/downlink beamforming under maximum power constraint.

IEEE INTERNET OF THINGS JOURNAL (2023)

Article Computer Science, Information Systems

HCFL: A High Compression Approach for Communication-Efficient Federated Learning in Very Large Scale IoT Networks

Minh-Duong Nguyen et al.

Summary: This paper proposes a high-compression federated learning (HCFL) scheme for very large scale IoT networks. The HCFL scheme reduces the data load and communication costs of FL processes, making them more adaptable on low-computing resource IoT devices. Additionally, the relationship between the number of IoT devices and the convergence level of the FL model is investigated to better assess the quality of the FL process.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2023)

Article Engineering, Electrical & Electronic

Evolution of NOMA Toward Next Generation Multiple Access (NGMA) for 6G

Yuanwei Liu et al.

Summary: Due to the growth in wireless devices and services, next generation wireless networks face unprecedented challenges. Advanced multiple access schemes, particularly non-orthogonal multiple access (NOMA), are being explored as a solution. This paper discusses the evolution of next generation multiple access (NGMA) and the potential techniques and mathematical tools involved.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2022)

Article Engineering, Electrical & Electronic

Non-Orthogonal Multiple Access Assisted Federated Learning via Wireless Power Transfer: A Cost-Efficient Approach

Yuan Wu et al.

Summary: This paper studies the Non-orthogonal Multiple Access (NOMA) assisted Federated Learning (FL) in wireless networks. It proposes a joint optimization algorithm for minimizing the system-wise cost by considering wireless power transfer, model transmission, and model aggregation. The proposed algorithm achieves the optimal solution and significantly reduces the system cost compared to traditional FL schemes.

IEEE TRANSACTIONS ON COMMUNICATIONS (2022)

Article Engineering, Electrical & Electronic

IRS-Assisted Downlink and Uplink NOMA in Wireless Powered Communication Networks

Bin Lyu et al.

Summary: This paper discusses the integration of intelligent reflecting surface (IRS) technology into non-orthogonal multiple access (NOMA) wireless powered communication networks (WPCNs). The proposed NOMA-based scheme achieves a considerable performance gain in uplink sum-rate while meeting the minimum rate requirement.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2022)

Article Engineering, Electrical & Electronic

Sum-Rate Maximization for Intelligent Reflecting Surface Assisted Terahertz Communications

Yijin Pan et al.

Summary: This paper presents a method using intelligent reflecting surface (IRS) to assist terahertz communications and proposes a block coordinate searching (BCS) algorithm to optimize the parameters of IRS. Simulation results show that the proposed scheme can significantly enhance system performance.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2022)

Article Engineering, Electrical & Electronic

Reconfigurable Intelligent Surface Enabled Vehicular Communication: Joint User Scheduling and Passive Beamforming

Ahmed Al-Hilo et al.

Summary: Reconfigurable intelligent surface (RIS) technology is integrated with vehicular communications to address dark zones and transmission distortions caused by obstacles, providing indirect wireless transmissions to disconnected areas within RSU coverage. The formulated problem of joint resource scheduling and passive beamforming for RIS is tackled using Deep Reinforcement Learning and Block Coordinate Descent (BCD), demonstrating superiority over baseline techniques in vehicular networks.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2022)

Article Engineering, Electrical & Electronic

Federated Learning via Intelligent Reflecting Surface

Zhibin Wang et al.

Summary: This paper proposes a method that leverages intelligent reflecting surface (IRS) for model aggregation to enhance the performance of federated learning (FL). Through optimizing device selection and beamforming design, the study achieved higher FL prediction accuracy.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2022)

Article Computer Science, Information Systems

Edge-Assisted Democratized Learning Toward Federated Analytics

Shashi Raj Pandey et al.

Summary: This research introduces a novel learning mechanism, called Edge-DemLearn, to enhance the generalization capability of federated analytics (FA). They utilize a distributed computing platform to build a distributed control and aggregation methodology, improving model performance and scalability of data analytics applications.

IEEE INTERNET OF THINGS JOURNAL (2022)

Article Engineering, Electrical & Electronic

Federated Learning With Non-IID Data in Wireless Networks

Zhongyuan Zhao et al.

Summary: This paper studies federated learning with non-IID data in wireless networks and proposes a federated averaging scheme and a joint optimization algorithm to reduce distribution divergence, maintaining a balance between model accuracy and cost. Simulation results show significant performance gains with a small price of latency and energy consumption.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2022)

Article Engineering, Electrical & Electronic

Integrating Over-the-Air Federated Learning and Non-Orthogonal Multiple Access: What Role Can RIS Play?

Wanli Ni et al.

Summary: This paper proposes a hybrid network utilizing RIS to optimize the performance of communication and computation. By decomposing the problem into non-convex and combinatorial problems, and using different optimization techniques to solve them, an alternating optimization algorithm is developed to tackle this complex issue.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2022)

Article Engineering, Electrical & Electronic

Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-Aided Over-the-Air Federated Learning

Jingheng Zheng et al.

Summary: This paper proposes a novel framework for balancing the accuracy and integrity of over-the-air federated learning (AirFL). The framework optimizes multi-antenna devices and base station (BS) jointly with a reconfigurable intelligent surface (RIS). Under perfect channel state information (CSI), the framework minimizes model distortion and maintains local model recoverability. Under imperfect CSI, it delivers a robust design to combat channel estimation errors.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2022)

Article Computer Science, Hardware & Architecture

DEVELOPING NOMA TO NEXT GENERATION MULTIPLE ACCESS: FUTURE VISION AND RESEARCH OPPORTUNITIES

Yuanwei Liu et al.

Summary: This article focuses on the application of NOMA in 6G networks, emphasizing the importance of Successive Interference Cancellation (SIC) and discussing the advantages and drawbacks of different SIC methods. It also explores meeting the new 6G performance requirements with NOMA and integrating it with new physical layer techniques, as well as introducing new application scenarios. Additionally, the article investigates machine learning in NOMA networks, bringing in the machine learning empowered NGMA era.

IEEE WIRELESS COMMUNICATIONS (2022)

Article Engineering, Electrical & Electronic

Federated Learning for Channel Estimation in Conventional and RIS-Assisted Massive MIMO

Ahmet M. Elbir et al.

Summary: This paper proposes a federated learning framework for channel estimation, which can train a convolutional neural network on local datasets to avoid large data transmission overhead. By designing FL-based channel estimation schemes for both conventional and RIS-assisted massive MIMO systems, the method reduces overhead by approximately 16 times compared to centralized learning while maintaining satisfactory performance.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2022)

Article Chemistry, Analytical

Sum Rate Optimization of IRS-Aided Uplink Muliantenna NOMA with Practical Reflection

Jihyun Choi et al.

Summary: Intelligent reflecting surfaces (IRSs) have emerged as a promising solution for enhancing performance in 6G networks. This research focuses on optimizing the reflection pattern of an IRS to maximize the sum rate in an uplink NOMA network. The study proposes different optimization methods for IRSs of varying sizes.

SENSORS (2022)

Article Computer Science, Information Systems

Federated Learning in Multi-RIS-Aided Systems

Wanli Ni et al.

Summary: This article investigates the use of multiple reconfigurable intelligent surfaces (RISs) to address the problem of model aggregation in federated learning systems. The seamless integration of communication and computation is achieved through over-the-air computation (AirComp), and the mean-square error (MSE) and device set in the model uploading process are optimized to improve the accuracy and convergence rate of federated learning.

IEEE INTERNET OF THINGS JOURNAL (2022)

Article Computer Science, Information Systems

STAR-RIS Integrated Nonorthogonal Multiple Access and Over-the-Air Federated Learning: Framework, Analysis, and Optimization

Wanli Ni et al.

Summary: This article integrates NOMA and AirFL using STAR-RIS for interference mitigation and coverage extension. The learning performance is significantly affected by beamforming schemes and wireless noise, and the optimality gap converges linearly as the learning rate decreases. By jointly designing transmit power and STAR-RIS configuration and utilizing iterative methods, a suboptimal solution for the MINLP problem is found.

IEEE INTERNET OF THINGS JOURNAL (2022)

Article Telecommunications

Sum Rate Maximization for IRS-Assisted Uplink NOMA

Ming Zeng et al.

Summary: An intelligent reflecting surface (IRS) is composed of low-cost reflecting elements that collaboratively steer incident signals to enhance system performance. Using semidefinite relaxation to handle the non-convex problem, the NOMA-based scheme achieves a larger sum rate than the OMA-based one. The impact of the number of reflecting elements on the sum rate is also revealed.

IEEE COMMUNICATIONS LETTERS (2021)

Article Engineering, Electrical & Electronic

A Joint Learning and Communications Framework for Federated Learning Over Wireless Networks

Mingzhe Chen et al.

Summary: This article discusses the challenges of training federated learning algorithms over a realistic wireless network and proposes an optimization model to minimize the FL loss function, providing a method to improve identification accuracy.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning

Wenqi Shi et al.

Summary: In this paper, a joint device scheduling and resource allocation policy is proposed to maximize model accuracy within a given total training time budget for latency constrained wireless FL. The accuracy maximization problem is decomposed into two sub-problems and solved accordingly. Experimental results demonstrate the superiority of the proposed policy under various settings.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

Non-Orthogonal Multiple Access (NOMA) With Multiple Intelligent Reflecting Surfaces

Yanyu Cheng et al.

Summary: This paper investigates the outage performance of NOMA networks assisted by IRSs with discrete phase shifts, deriving asymptotic expressions for the upper and lower bounds of outage probability in the high SNR regime, and obtaining the diversity order. Results show that a 3-bit resolution for IRSs achieves near-optimal outage performance, indicating the superiority of IRSs over full-duplex decode-and-forward relays.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

Reconfigurable Intelligent Surface Enabled Federated Learning: A Unified Communication-Learning Design Approach

Hang Liu et al.

Summary: Federated learning is proposed as an attractive substitute for centralized machine learning to exploit massive amounts of data generated at mobile edge networks. However, the straggler issue in over-the-air FL, caused by the heterogeneity of communication capacities among edge devices, remains a challenge despite efforts to alleviate it through device selection.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2021)

Article Computer Science, Hardware & Architecture

Federated Learning for Industrial Internet of Things in Future Industries

Dinh C. Nguyen et al.

Summary: Industrial Internet of Things (IIoT) offers promising opportunities for revolutionizing industrial systems operation, and Artificial Intelligence (AI) is widely utilized in intelligent IIoT applications, with Federated Learning (FL) emerging as an attractive collaborative AI approach that can protect user privacy and confidential information in modern IIoT networks. Open research topics need to be addressed for the full realization of FL-IIoT in future industries.

IEEE WIRELESS COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

Intelligent Spectrum Learning for Wireless Networks With Reconfigurable Intelligent Surfaces

Bo Yang et al.

Summary: The study introduces the concept of intelligent spectrum learning and utilizes convolutional neural network to help RIS identify interfering signals, maximizing the received signal interference plus noise ratio through dynamically configuring RIS elements. Simulation results show performance enhancement with deep learning and demonstrate the superiority of the ISL-aided approach.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2021)

Article Engineering, Electrical & Electronic

Capacity and Optimal Resource Allocation for IRS-Assisted Multi-User Communication Systems

Xidong Mu et al.

Summary: This article investigates the fundamental capacity limits of intelligent reflecting surface (IRS)-assisted multi-user wireless communication systems, characterizing the capacity and rate regions for both NOMA and OMA transmission schemes. Numerical results show that a significant capacity and rate region improvement can be achieved by using IRS, and the capacity gain can be further improved by dynamically configuring the IRS reflection matrix.

IEEE TRANSACTIONS ON COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

Resource Allocation for Multi-Cell IRS-Aided NOMA Networks

Wanli Ni et al.

Summary: This article introduces a novel resource allocation framework for multi-cell intelligent reflecting surface (IRS) aided non-orthogonal multiple access (NOMA) networks. Numerical results demonstrate the significant increase in network sum rate with the use of IRS, higher energy efficiency of proposed algorithms for multi-cell IRS-aided NOMA networks, and the ability to adjust the balance between coverage area and spectrum efficiency by selecting the location of the IRS.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2021)

Article Engineering, Electrical & Electronic

6G Wireless Systems: Vision, Requirements, Challenges, Insights, and Opportunities

Harsh Tataria et al.

Summary: This article discusses the generational changes in mobile communications, with a focus on the technical requirements, challenges, and possibilities of the sixth generation (6G) wireless systems. With the increasing demand for spectrum utilization, 6G systems will operate in a wider range of frequency bands.

PROCEEDINGS OF THE IEEE (2021)

Article Computer Science, Information Systems

IRS-Assisted Wireless Powered NOMA: Do We Really Need Different Phase Shifts in DL and UL?

Qingqing Wu et al.

Summary: Intelligent reflecting surface (IRS) technology can improve the efficiency of WPCNs by reconfiguring signal propagation environments, and maximizing the total throughput of all devices through joint optimization of IRS phase shifts and resource allocation.

IEEE WIRELESS COMMUNICATIONS LETTERS (2021)

Article Engineering, Electrical & Electronic

Improving Physical Layer Security for Reconfigurable Intelligent Surface Aided NOMA 6G Networks

Zhe Zhang et al.

Summary: This paper investigates the physical layer security (PLS) for a RIS-aided NOMA 6G networks, where a RIS is deployed to assist two dead zone NOMA users and internal/external eavesdropping are considered. The proposed joint beamforming and power allocation scheme aims to improve system PLS, with superior performance shown in simulation results. Increasing the number of reflecting elements is found to bring more gain in secrecy performance than increasing the number of transmit antennas.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2021)

Article Engineering, Electrical & Electronic

Dynamic Network Service Selection in IRS-Assisted Wireless Networks: A Game Theory Approach

Nguyen Luong et al.

Summary: This article explores the dynamic network service provider and service selection in a user-centric network using an evolutionary game approach. Users adjust their selections of providers and services based on utilities, and simulations demonstrate the consistency and effectiveness of the proposed method.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2021)

Article Computer Science, Information Systems

Delay-Optimal Scheduling for IRS-Aided Mobile Edge Computing

Fasheng Zhou et al.

Summary: The study introduces an intelligent reflecting surface (IRS)-aided mobile edge computing system to minimize the total delay of two users, considering IRS passive reflection design and user computation offloading scheduling. A new flexible time-sharing NOMA scheme that includes both conventional NOMA and TDMA as special cases is proposed, and the preference for NOMA and TDMA based transmissions in different scenarios is discussed based on users' cloud-computing time and rate discrepancy.

IEEE WIRELESS COMMUNICATIONS LETTERS (2021)

Article Computer Science, Information Systems

A Maximum Throughput Design for Wireless Powered Communication Networks With IRS-NOMA

Dongyeong Song et al.

Summary: This study examines wireless powered communication networks with a hybrid access-point, an intelligent reflecting surface, and multiple users. By jointly optimizing the transmit time, power, and phase shifts induced by the IRS, the sum-throughput of the network is maximized, enhancing system performance.

IEEE WIRELESS COMMUNICATIONS LETTERS (2021)

Article Engineering, Electrical & Electronic

Scheduling Policies for Federated Learning in Wireless Networks

Howard H. Yang et al.

IEEE TRANSACTIONS ON COMMUNICATIONS (2020)

Article Telecommunications

Intelligent Reflecting Surface-Assisted Multiple Access With User Pairing: NOMA or OMA?

Beixiong Zheng et al.

IEEE COMMUNICATIONS LETTERS (2020)

Article Engineering, Electrical & Electronic

Federated Learning: Challenges, Methods, and Future Directions

Tian Li et al.

IEEE SIGNAL PROCESSING MAGAZINE (2020)

Article Engineering, Electrical & Electronic

Federated Learning for Wireless Communications: Motivation, Opportunities, and Challenges

Solmaz Niknam et al.

IEEE COMMUNICATIONS MAGAZINE (2020)

Article Computer Science, Hardware & Architecture

A Vision of 6G Wireless Systems: Applications, Trends, Technologies, and Open Research Problems

Walid Saad et al.

IEEE NETWORK (2020)

Article Telecommunications

Federated learning for 6G communications: Challenges, methods, and future directions

Yi Liu et al.

China Communications (2020)

Article Engineering, Electrical & Electronic

Auction Mechanism for Dynamic Bandwidth Allocation in Multi-Tenant Edge Computing

Tra Huong Thi Le et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Article Engineering, Electrical & Electronic

Adaptive Federated Learning With Gradient Compression in Uplink NOMA

Haijian Sun et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Proceedings Paper Computer Science, Artificial Intelligence

A Stackelberg Game Approach to Resource Allocation for IRS-aided Communications

Yulan Gao et al.

2020 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM) (2020)

Proceedings Paper Engineering, Electrical & Electronic

Convergence Time Minimization of Federated Learning over Wireless Networks

Mingzhe Chen et al.

ICC 2020 - 2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC) (2020)

Article Engineering, Electrical & Electronic

Multi-Armed Bandit-Based Client Scheduling for Federated Learning

Wenchao Xia et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2020)

Article Engineering, Electrical & Electronic

Exploiting Intelligent Reflecting Surfaces in NOMA Networks: Joint Beamforming Optimization

Xidong Mu et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2020)

Article Engineering, Electrical & Electronic

Energy-Efficient Design of IRS-NOMA Networks

Fang Fang et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2020)

Article Engineering, Electrical & Electronic

Adaptive Federated Learning in Resource Constrained Edge Computing Systems

Shiqiang Wang et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2019)

Article Engineering, Electrical & Electronic

Power Minimizing Beamforming and Power Allocation for MISO-NOMA Systems

Yeonjin Jeong et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2019)

Article Engineering, Electrical & Electronic

Incentivizing Device-to-Device Load Balancing for Cellular Networks: An Online Auction Design

Mohammad H. Hajiesmaili et al.

IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS (2017)

Article Engineering, Electrical & Electronic

Enabling Radio-as-a-Service With Truthful Auction Mechanisms

Jing Wang et al.

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS (2017)

Article Computer Science, Information Systems

Virtualization of 5G Cellular Networks as a Hierarchical Combinatorial Auction

Kun Zhu et al.

IEEE TRANSACTIONS ON MOBILE COMPUTING (2016)

Article Computer Science, Information Systems

Markov Approximation for Combinatorial Network Optimization

Minghua Chen et al.

IEEE TRANSACTIONS ON INFORMATION THEORY (2013)

Article Mathematics, Applied

Complex quadratic optimization and semidefinite programming

SZ Zhang et al.

SIAM JOURNAL ON OPTIMIZATION (2006)